| | |
| | import spacy |
| | from collections import Counter |
| |
|
| | |
| | POS_COLORS = { |
| | 'ADJ': '#FFA07A', |
| | 'ADP': '#98FB98', |
| | 'ADV': '#87CEFA', |
| | 'AUX': '#DDA0DD', |
| | 'CCONJ': '#F0E68C', |
| | 'DET': '#FFB6C1', |
| | 'INTJ': '#FF6347', |
| | 'NOUN': '#90EE90', |
| | 'NUM': '#FAFAD2', |
| | 'PART': '#D3D3D3', |
| | 'PRON': '#FFA500', |
| | 'PROPN': '#20B2AA', |
| | 'SCONJ': '#DEB887', |
| | 'SYM': '#7B68EE', |
| | 'VERB': '#FF69B4', |
| | 'X': '#A9A9A9', |
| | } |
| |
|
| | POS_TRANSLATIONS = { |
| | 'es': { |
| | 'ADJ': 'Adjetivo', |
| | 'ADP': 'Adposici贸n', |
| | 'ADV': 'Adverbio', |
| | 'AUX': 'Auxiliar', |
| | 'CCONJ': 'Conjunci贸n Coordinante', |
| | 'DET': 'Determinante', |
| | 'INTJ': 'Interjecci贸n', |
| | 'NOUN': 'Sustantivo', |
| | 'NUM': 'N煤mero', |
| | 'PART': 'Part铆cula', |
| | 'PRON': 'Pronombre', |
| | 'PROPN': 'Nombre Propio', |
| | 'SCONJ': 'Conjunci贸n Subordinante', |
| | 'SYM': 'S铆mbolo', |
| | 'VERB': 'Verbo', |
| | 'X': 'Otro', |
| | }, |
| | 'en': { |
| | 'ADJ': 'Adjective', |
| | 'ADP': 'Adposition', |
| | 'ADV': 'Adverb', |
| | 'AUX': 'Auxiliary', |
| | 'CCONJ': 'Coordinating Conjunction', |
| | 'DET': 'Determiner', |
| | 'INTJ': 'Interjection', |
| | 'NOUN': 'Noun', |
| | 'NUM': 'Number', |
| | 'PART': 'Particle', |
| | 'PRON': 'Pronoun', |
| | 'PROPN': 'Proper Noun', |
| | 'SCONJ': 'Subordinating Conjunction', |
| | 'SYM': 'Symbol', |
| | 'VERB': 'Verb', |
| | 'X': 'Other', |
| | }, |
| | 'fr': { |
| | 'ADJ': 'Adjectif', |
| | 'ADP': 'Adposition', |
| | 'ADV': 'Adverbe', |
| | 'AUX': 'Auxiliaire', |
| | 'CCONJ': 'Conjonction de Coordination', |
| | 'DET': 'D茅terminant', |
| | 'INTJ': 'Interjection', |
| | 'NOUN': 'Nom', |
| | 'NUM': 'Nombre', |
| | 'PART': 'Particule', |
| | 'PRON': 'Pronom', |
| | 'PROPN': 'Nom Propre', |
| | 'SCONJ': 'Conjonction de Subordination', |
| | 'SYM': 'Symbole', |
| | 'VERB': 'Verbe', |
| | 'X': 'Autre', |
| | } |
| | } |
| |
|
| | def get_repeated_words_colors(doc): |
| | word_counts = Counter(token.text.lower() for token in doc if token.pos_ != 'PUNCT') |
| | repeated_words = {word: count for word, count in word_counts.items() if count > 1} |
| |
|
| | word_colors = {} |
| | for token in doc: |
| | if token.text.lower() in repeated_words: |
| | word_colors[token.text.lower()] = POS_COLORS.get(token.pos_, '#FFFFFF') |
| |
|
| | return word_colors |
| |
|
| | def highlight_repeated_words(doc, word_colors): |
| | highlighted_text = [] |
| | for token in doc: |
| | if token.text.lower() in word_colors: |
| | color = word_colors[token.text.lower()] |
| | highlighted_text.append(f'<span style="background-color: {color};">{token.text}</span>') |
| | else: |
| | highlighted_text.append(token.text) |
| | return ' '.join(highlighted_text) |